4b_sft_checkpoint-30 / trainer_state.json
Ibisbill's picture
Upload checkpoint-30
0ae9922 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.11121408711770157,
"eval_steps": 1000,
"global_step": 30,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0037071362372567192,
"grad_norm": 4.805793835959296,
"learning_rate": 0.0,
"loss": 0.4732,
"step": 1
},
{
"epoch": 0.0074142724745134385,
"grad_norm": 4.999676761082255,
"learning_rate": 1.8518518518518518e-07,
"loss": 0.5107,
"step": 2
},
{
"epoch": 0.011121408711770158,
"grad_norm": 4.864588159866656,
"learning_rate": 3.7037037037037036e-07,
"loss": 0.4708,
"step": 3
},
{
"epoch": 0.014828544949026877,
"grad_norm": 5.136331269447859,
"learning_rate": 5.555555555555555e-07,
"loss": 0.5024,
"step": 4
},
{
"epoch": 0.018535681186283594,
"grad_norm": 4.731519955515801,
"learning_rate": 7.407407407407407e-07,
"loss": 0.4598,
"step": 5
},
{
"epoch": 0.022242817423540315,
"grad_norm": 4.567784280784228,
"learning_rate": 9.259259259259259e-07,
"loss": 0.4717,
"step": 6
},
{
"epoch": 0.025949953660797033,
"grad_norm": 4.522993398842187,
"learning_rate": 1.111111111111111e-06,
"loss": 0.4649,
"step": 7
},
{
"epoch": 0.029657089898053754,
"grad_norm": 2.864282407749261,
"learning_rate": 1.2962962962962962e-06,
"loss": 0.4499,
"step": 8
},
{
"epoch": 0.033364226135310475,
"grad_norm": 2.781272716749165,
"learning_rate": 1.4814814814814815e-06,
"loss": 0.4952,
"step": 9
},
{
"epoch": 0.03707136237256719,
"grad_norm": 2.546317122615437,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.4487,
"step": 10
},
{
"epoch": 0.04077849860982391,
"grad_norm": 2.700137363750789,
"learning_rate": 1.8518518518518519e-06,
"loss": 0.4335,
"step": 11
},
{
"epoch": 0.04448563484708063,
"grad_norm": 2.7541576896447233,
"learning_rate": 2.037037037037037e-06,
"loss": 0.4371,
"step": 12
},
{
"epoch": 0.04819277108433735,
"grad_norm": 2.8211373607312447,
"learning_rate": 2.222222222222222e-06,
"loss": 0.4374,
"step": 13
},
{
"epoch": 0.051899907321594066,
"grad_norm": 2.762988661288179,
"learning_rate": 2.4074074074074075e-06,
"loss": 0.4609,
"step": 14
},
{
"epoch": 0.05560704355885079,
"grad_norm": 2.0744764582695923,
"learning_rate": 2.5925925925925925e-06,
"loss": 0.3954,
"step": 15
},
{
"epoch": 0.05931417979610751,
"grad_norm": 2.0106943337826277,
"learning_rate": 2.7777777777777783e-06,
"loss": 0.3589,
"step": 16
},
{
"epoch": 0.06302131603336422,
"grad_norm": 1.9151145546731518,
"learning_rate": 2.962962962962963e-06,
"loss": 0.374,
"step": 17
},
{
"epoch": 0.06672845227062095,
"grad_norm": 1.7742581344696668,
"learning_rate": 3.1481481481481483e-06,
"loss": 0.4013,
"step": 18
},
{
"epoch": 0.07043558850787766,
"grad_norm": 1.5873818678054419,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.3847,
"step": 19
},
{
"epoch": 0.07414272474513438,
"grad_norm": 1.1782654410938447,
"learning_rate": 3.5185185185185187e-06,
"loss": 0.3392,
"step": 20
},
{
"epoch": 0.0778498609823911,
"grad_norm": 1.2100197827995287,
"learning_rate": 3.7037037037037037e-06,
"loss": 0.3174,
"step": 21
},
{
"epoch": 0.08155699721964782,
"grad_norm": 1.3105688995199969,
"learning_rate": 3.88888888888889e-06,
"loss": 0.3774,
"step": 22
},
{
"epoch": 0.08526413345690455,
"grad_norm": 1.0431241378849054,
"learning_rate": 4.074074074074074e-06,
"loss": 0.3329,
"step": 23
},
{
"epoch": 0.08897126969416126,
"grad_norm": 0.8631707844136063,
"learning_rate": 4.2592592592592596e-06,
"loss": 0.2954,
"step": 24
},
{
"epoch": 0.09267840593141798,
"grad_norm": 0.890999961539687,
"learning_rate": 4.444444444444444e-06,
"loss": 0.3143,
"step": 25
},
{
"epoch": 0.0963855421686747,
"grad_norm": 0.8696087553408013,
"learning_rate": 4.62962962962963e-06,
"loss": 0.3012,
"step": 26
},
{
"epoch": 0.10009267840593142,
"grad_norm": 0.9182891405006179,
"learning_rate": 4.814814814814815e-06,
"loss": 0.2918,
"step": 27
},
{
"epoch": 0.10379981464318813,
"grad_norm": 0.9323649589307044,
"learning_rate": 5e-06,
"loss": 0.2953,
"step": 28
},
{
"epoch": 0.10750695088044486,
"grad_norm": 0.812755436108598,
"learning_rate": 5.185185185185185e-06,
"loss": 0.3003,
"step": 29
},
{
"epoch": 0.11121408711770157,
"grad_norm": 0.7059616195446038,
"learning_rate": 5.370370370370371e-06,
"loss": 0.2843,
"step": 30
}
],
"logging_steps": 1,
"max_steps": 538,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8820667908096.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}